锅炉汽温对象逆动力学过程模糊辨识

建立热力系统逆动力学过程模型是热力系统逆动力学研究及应用的关键。该文报告了一种锅炉汽温对象逆动力学过程模型的模糊在线辨识方法与结果。通过聚类和竞争学习算法，对逆动力学模型输入数据空间进行分区，在每个局部的数据子空间上，利用递推最小二乘辨识算法建立逆动力学过程模糊规则，并通过自适应模糊推理实现系统输入过程的反演。仿真结果表明，所建立的逆动力学过程模型对时变汽温对象具有良好的自适应能力和在线跟踪能力；通过汽温对象逆动力学过程在线辨识，能够获得恰当的控制过程，保证系统输出温度按照预定的轨迹达到设定值。     

基于局部神经网络模型的过热汽温多模型预测控制的研究

针对锅炉过热汽温的特点，设计串级过热汽温控制系统。主调节器采用基于局部神经网络模型的多模型预测控制，即由主蒸汽流量确定的不同工作点，用神经网络建立局部动态模型，进而建立一组局部神经网络预测控制器，然后通过加权合成的方式获得最终的控制信号；副调节器采用基于多个简单比例控制器的加权合成比例控制。该控制方案融合了神经网络、多模型控制和预测控制的特点。仿真结果表明，在负荷大范围变化的工况下，控制系统仍保持了良好的控制性能，具有较强的鲁棒性。     

基于模糊规则的热工过程非线性模型的研究

建立精确的热工过程整体模型是对热工过程进行全局优化控制的基础，而热工过程往往具有非线性和不确定性，传统的描述热工过程动态数学模型的方法（如传递函数等）难以建立非线性模型，从而难于精确表达热工过程及实施整体优化控制，该文提出了一类实用的基于模糊规则的热工过程非线性建模方法，具体为：首先通过聚类和竞争学习算法，对热工过程的输入数据空间进行分区，然后在每个局部的数据子空间上，利用递推的最小二乘辨识算法（RLS）建立一个基于模糊规则的局部线性动态模型，这样，一个典型的非线性热工过程可以通过一组基于模糊规则的线性模型来表示。计算结果表明：基于模糊规则的非线性模糊模型，不仅能精确地描述过程的非线性，而且算法简单，实用。     

基于模糊建模技术的PEMFC非线性控制

针对PEMFC等一类具有严重非线性的复杂被控对象,提出一种基于模糊模型的非线性预测控制算法对PEM-FC系统进行建模与控制。在建模与控制过程中,采用离线学习和在线修正辨识出对象的模糊模型;其中,模型的参数通过模糊聚类初始化和离线反向传播算法进行学习,必要时,可通过在线调整后件参数,使模型的预测精度能满足实时控制的需要。线性辨识方法在线建立PEMFC控制系统的T-S模糊预测模型,然后基于分支定界法的基本原理对控制量进行离散寻优,从而实现PEMFC的非线性预测控制。仿真和实验结果证明了该算法的有效性和优越性。     

多变量汽温模糊预测控制

针对火电厂锅炉汽温对象具有大迟延、非线性时变的特性,提出一种基于T-S模糊模型的多输入多输出(MIMO)预测控制策略.将MIMO系统分解为多个多输入单输出(MISO)系统,利用T-S模糊模型描述对象的动态特性,模糊规则将非线性对象划分为多个局部子线性模型,并用加权最小二乘法辨识其参数,然后用预测函数原理设计控制器.为提高预测控制性能,采用多步线性化模型构成多步预报器.仿真结果表明对于MIMO系统的长期预报和控制,多步线性化模型预测控制性能优于单步线性化模型预测控制性能.     

基于模糊预测控制技术的注汽锅炉干度控制系统

为了实现对注汽锅炉干度的高质量控制,设计了一个基于模糊预测控制的干度控制系统,该系统通过对历史数据的自适应学习获得初始预测模型,并采用误差反向传播学习算法对模型参数进行优化,然后根据模型输出得出控制律,实现对干度的调节,因而具有较强的鲁棒性和自适应能力。实际应用表明,系统具有良好的控制效果。     

基于免疫原理的自适应模糊控制器优化设计

利用免疫系统的克隆选择原理设计了全局搜索优化算法和局部搜索优化算法，并提出了一种时变对象的模糊控制器参数自整定方案。该方案利用全局优化算法离线组合优化标称参数下的控制器，对象发生变化后，利用局部优化算法在线优化，可快速获得新的控制器参数，以实现自适应控制。仿真结果表明，该控制系统在被控对象参数变化的情况下，仍具有良好的控制性能，能够对一类时变对象实施高精度控制，具有较大的工程应用价值。     

锅炉蒸汽温度模型预测控制

针对锅炉蒸汽温度(汽温)模型预测控制在机组大范围负荷变动工况下的适应性问题，通过机理性分析和锅炉换热设备的特性建立了汽温对象的多机理模型，利用粒子群算法对所建模型进行修正，并引入了模糊切换功能，使模型能够更加精确地描述实际气温变化过程，提高了其自适应性和预测控制的可靠性。     

基于NSPSO算法的微调模糊宽度学习系统用于非线性系统辨识

非线性系统的辨识涉及对对象的控制输入和输出之间的关系进行近似。其中，模糊宽度学习系统是一种新颖的且具有潜力的非线性系统辨识方法。然而，该方法在辨识过程中存在性能不足且超参数敏感的问题。为此，本文提出了一种基于节点敏感性粒子群算法的微调模糊宽度学习系统，用于求解非线性系统辨识问题。首先，本文在原始模糊宽度学习系统结构基础上使用稀疏自编码器对后件参数进行微调，构建了一种新型的微调模糊宽度学习系统。然后，提出了一种节点敏感性PSO算法对模糊宽度学习系统的模糊规则、TSK模糊子系统和增强节点三个参数进行搜索。使用模拟的非线性系统生成的数据验证模型的有效性，并利用经过节点敏感性PSO优化搜索的最优微调模糊宽度学习系统结构进行预测。该模型计算过程简单高效，能够同时用于神经网络逼近和模糊推理，具有快速确定最优模型结构的优点，可以有效提升模型的非线性系统辨识能力，在非线性系统辨识任务中具有较强的应用价值。     

基于模糊算法的自适应忆阻PI控制系统设计

为了解决传统模拟PI控制器参数不易整定以及面对被控对象发生变化时无法在线进行参数调整的问题，引入了忆阻器件实现了控制器参数可在线调整。同时针对忆阻器阻值大小不易确定的问题，引入了模糊算法，将模糊算法与忆阻PI控制器进行结合，设计了一种模糊忆阻PI控制系统，实现了控制器参数的自适应调整。在理论推导的基础上，进行了Multisim仿真与电路实验。结果表明，基于模糊算法的自适应忆阻PI控制系统与传统模拟PI控制器相比，参数可以进行在线调整，具有较强的自适应能力，且基于模糊算法的自适应忆阻PI控制系统可以将系统的超调量降低66.27%，具有更好的跟踪性能。     

Dynamic preventive control strategies for power systems considering transient and midterm stabilities

This paper proposes a new dynamic preventive control strategy to maintain power system security, in terms of both transient and midterm stabilities. While the authors have already presented preventive control strategies for transient stability, a new problem has arisen in midterm instability in which some generators lose synchronism after 10 seconds or more from a fault clearance. It is clear that the cause of the instability is mainly post-contingency dynamic steady-state instability. This paper first shows a preventive control strategy for improving midterm stability using a dominant eigenvalue of post-contingency equilibrium point. This paper also presents a unified dynamic preventive control algorithm that can maintain both stabilities together. In this algorithm, the time domain for each stability problem is considered appropriately and the difference between the classical model and the detailed model is analyzed in detail. The effectiveness of the proposed method is examined with numerical examples for a model system.     

基于DMPC和储能单元约束的分组一致性控制策略

针对多个电池储能单元间的分布式协调控制问题,提出了一种分布式储能单元分组一致性控制策略。首先,提出了一种基于分布式模型预测控制和状态约束的加权一致性算法,能考虑各储能单元的功率约束条件并快速完成多储能单元的功率分配。其次,提出了一种储能单元分组控制策略。根据荷电状态(state of change, SOC)信息设定储能单元的权重,达到改善储能单元SOC的一致性的目的。同时基于所提一致性算法,制定储能单元组间协调控制策略和储能单元效率提升策略,从而达到改善储能系统调节能力、延长储能系统寿命和提升能量转换效率的目的。最后,在Matlab中构建含8个电池储能单元的微电网系统,对所提算法和控制策略进行仿真分析。仿真结果表明,所提算法和控制策略在提升收敛速度、优化控制效果、延长储能系统寿命以及提升储能系统运行效率方面均具有一定优势。     

Adaptive control in a heating vessel: A comparative study

This paper presents experimental results obtained in temperature adaptive control of a heating vessel. A non-linear model of the process showed that the feed flow rate causes severe variations in time constant and process gain. An extended horizon self-tuning controller and two different model reference adaptive controllers were tested. The influence of design parameters on control performance for each algorithm was assessed. The control system was disturbed with load and setpoint changes.     

Analysis and performance improvement of motor speed control system with nonlinear friction

Solid friction in machine elements is one of the dominant nonlinearities affecting the control accuracy of servo drive systems. Many schemes, including feedforward control, observer-based control and repetitive learning control have been proposed to compensate for nonlinear friction. These schemes show superior performance compared to that of the conventional P- and/or PI-controller; however, friction model errors and bandwidth restriction of the observer cause compensation errors, thus decreasing control accuracy. This paper presents a new control algorithm for performance improvement of a motor speed control system having nonlinear friction. By analyzing characteristics of conventional compensation control schemes during velocity reversal, the relation between control parameters and control accuracy is examined so as to explore problems with each scheme. Based on these analyses, a new feedforward control algorithm is proposed. The proposed algorithm is verified by analyses of control characteristics and experiments using a prototype. Experimental results show the superior performance improvement of the proposed algorithm.     

Traffic monitoring and accident detection at intersections

We have developed an algorithm, referred to as spatio-temporal Markov random field, for traffic images at intersections. This algorithm models a tracking problem by determining the state of each pixel in an image and its transit, and how such states transit along both the x-y image axes as well as the time axes. Our algorithm is sufficiently robust to segment and track occluded vehicles at a high success rate of 93%-96%. This success has led to the development of an extendable robust event recognition system based on the hidden Markov model (HMM). The system learns various event behavior patterns of each vehicle in the HMM chains and then, using the output from the tracking system, identifies current event chains. The current system can recognize bumping, passing, and jamming. However, by including other event patterns in the training set, the system can be extended to recognize those other events, e.g., illegal U-turns or reckless driving. We have implemented this system, evaluated it using the tracking results, and demonstrated its effectiveness     

Modeling and Recognition of Driving Behavior Based on Stochastic Switched ARX Model

This paper presents the development of the modeling and recognition of human driving behavior based on a stochastic switched autoregressive exogenous (SS-ARX) model. First, a parameter estimation algorithm for the SS-ARX model with multiple measured input-output sequences is developed based on the expectation-maximization algorithm. This can be achieved by extending the parameter estimation technique for the conventional hidden Markov model. Second, the developed parameter estimation algorithm is applied to driving data with the focus being on driver's collision avoidance behavior. The driving data were collected using a driving simulator based on the cave automatic virtual environment, which is a stereoscopic immersive virtual reality system. Then, the parameter set for each driver is obtained, and certain driving characteristics are identified from the viewpoint of switched control mechanism. Finally, the performance of the SS-ARX model as a behavior recognizer is examined. The results show that the SS-ARX model holds remarkable potential to function as a behavior recognizer.     

高校教室灯光节能控制系统的设计

高校教室灯光节能控制系统是基于改变高校教室由于"长明灯"造成的能源浪费现状,而设计的低成本节能系统。该系统通过RS485通讯建立的主从网络实时控制各区域灯光的亮灭,而且采用多模式控制,实现了各模式间的自动转换。系统利用时间、光强和人员分布作为控制依据,通过一定的控制算法,使系统控制达到了较好的节能效果。     

Neural Networks for Real-Time Traffic Signal Control

Real-time traffic signal control is an integral part of the urban traffic control system, and providing effective real-time traffic signal control for a large complex traffic network is an extremely challenging distributed control problem. This paper adopts the multiagent system approach to develop distributed unsupervised traffic responsive signal control models, where each agent in the system is a local traffic signal controller for one intersection in the traffic network. The first multiagent system is developed using hybrid computational intelligent techniques. Each agent employs a multistage online learning process to update and adapt its knowledge base and decision-making mechanism. The second multiagent system is developed by integrating the simultaneous perturbation stochastic approximation theorem in fuzzy neural networks (NN). The problem of real-time traffic signal control is especially challenging if the agents are used for an infinite horizon problem, where online learning has to take place continuously once the agent-based traffic signal controllers are implemented into the traffic network. A comprehensive simulation model of a section of the Central Business District of Singapore has been developed using PARAMICS microscopic simulation program. Simulation results show that the hybrid multiagent system provides significant improvement in traffic conditions when evaluated against an existing traffic signal control algorithm as well as the SPSA-NN-based multiagent system as the complexity of the simulation scenario increases. Using the hybrid NN-based multiagent system, the mean delay of each vehicle was reduced by 78% and the mean stoppage time, by 85% compared to the existing traffic signal control algorithm. The promising results demonstrate the efficacy of the hybrid NN-based multiagent system in solving large-scale traffic signal control problems in a distributed manner.     

Robust multimachine power systems control via high order sliding modes

This article presents a formal study of the transient stabilization problem, including a stability proof. A decentralized nonlinear robust control scheme for multimachine electrical power systems is presented. The mathematical model takes into account the interconnections between electrical elements of the power system such as generators, electric networks, loads and exciters. Each generator is considered as a seventh order system that includes the mechanical and rotor electrical dynamics with static exciter dynamics. The proposed control scheme is based on the Block Control methodology and Second Order Sliding Modes technique using the Super Twisting algorithm. A nonlinear observer is designed to estimate the rotor fluxes of the synchronous machines. The designed decentralized control scheme requires the only local information for each local controller. This control scheme was tested through simulation on the well known reduced 9 buses equivalent model of the WSCC system.     

混合能源协同控制的智能家庭能源优化控制策略

家庭能源优化控制是家庭能源管理系统(HEMS)的重要分支之一,然而由于缺少有效的智能优化算法,制约了家庭能源优化控制的实际应用。本文通过对家用电器运行特性的分析,将家庭用电设备分为刚性负荷,简单可调节负荷,电池类设备,供暖、通风和空调(HVAC)系统设备等,并建立相应的负荷模型;以市电电网、光伏发电、储能电池三种能源作为智能家庭的供给源,以电能花费和用户舒适度作为优化目标,建立混合能源协同控制的智能家庭能源优化控制模型;并提出一种基于改进的快速粒子群算法(APSOA)的智能求解方法,得出每个电器最优的用电时段,室温控制系统各个时段所需功率以及蓄电池各个时段的充放电功率。以某智能家庭夏季某一天用电情况为例,在Matlab环境下,建立模型并仿真,与粒子群算法(PSOA)、遗传算法(GA)进行对比,说明了模型和算法的可行性及有效性。